geo-data-collector

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill's examples and templates embed proxy usernames/passwords directly into curl commands and code (e.g., USER:PASS in proxy URLs), which requires inserting real secret values verbatim into generated commands or code—an explicit high-risk exfiltration pattern.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to fetch and scrape public third‑party websites (e.g., e-commerce product pages, Google SERPs, ads, Amazon storefronts and publisher sites) using country-targeted proxies and a browser tool (see "Use Case 1: Price Monitoring", "Use Case 2: Localized Search Results (SERP)", and "Use Case 5: Localized Review Collection"), so untrusted user-generated/open web content is ingested and can materially influence subsequent tool use and decisions.